Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 11060
    Prev
    Next
    INDEX
    Explanations

    spiritual expressions and requests for divine support or strength

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows verbs like "give", "take", or indicates a source of something

    np_acts-logits-general · gemini-2.0-flash

    give me sustenance and strength

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     amuse
    -0.41
    Fun
    -0.40
     surla
    -0.39
    CROSSTALK
    -0.39
     fun
    -0.39
     uſe
    -0.38
    Odkazy
    -0.38
    erdings
    -0.38
    ագրություններ
    -0.38
     amusing
    -0.37
    POSITIVE LOGITS
     Taktlose
    0.55
    HomeAsUpEnabled
    0.50
    хьтан
    0.49
     yyr
    0.48
    Spoljašnje
    0.45
    NewGuid
    0.43
    expandindo
    0.43
    AsUp
    0.42
     мәкал
    0.41
    GEBURTSDATUM
    0.40
    Activations Density 0.099%

    No Known Activations